Anurag Kumar

speech enhancement (5) multimodal learning (5) transfer learning (4) spatial audio (4) deep neural network (3) audio-visual learning (3) speech quality assessment (2) neural network (2) weakly supervised learning (2) non-matching reference (2) room impulse response (2) neural radiance field (2) mean opinion score (2) speaker separation (2) time-domain audio (2) multi-modal learning (1) egocentric vision (1) self-supervised learning (1) matrix factorization (1) domain generalization (1)